Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 52 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2185. Min Range: -4.2185
Max Act: 4.2185. Min Act: -0.1700
Data Index: 426288 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2185. Min Range: -4.2185
Max Act: 4.1247. Min Act: -0.1700
Data Index: 1065854 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2185. Min Range: -4.2185
Max Act: 4.0622. Min Act: -0.1700
Data Index: 1338371 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2185. Min Range: -4.2185
Max Act: 4.0309. Min Act: -0.1700
Data Index: 864868 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9996. Min Act: -0.1700
Data Index: 573417 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9996. Min Act: -0.1700
Data Index: 203062 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2185. Min Range: -4.2185
Max Act: 4.0309. Min Act: -0.1700
Data Index: 1047216 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2185. Min Range: -4.2185
Max Act: 4.0309. Min Act: -0.1700
Data Index: 1306622 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9684. Min Act: -0.1700
Data Index: 610755 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9684. Min Act: -0.1700
Data Index: 80793 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9684. Min Act: -0.1700
Data Index: 341324 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9058. Min Act: -0.1700
Data Index: 690500 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9058. Min Act: -0.1700
Data Index: 1286894 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9058. Min Act: -0.1700
Data Index: 483852 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9058. Min Act: -0.1700
Data Index: 951009 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9058. Min Act: -0.1700
Data Index: 434478 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9058. Min Act: -0.1700
Data Index: 746442 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.9371. Min Act: -0.1700
Data Index: 802134 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.8746. Min Act: -0.1700
Data Index: 773718 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2185. Min Range: -4.2185
Max Act: 3.8746. Min Act: -0.1700
Data Index: 136702 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19